Fire Detection inImages Using FrameworkBased on Image Processing, Motion Detection and Convolutional Neural Network

Abstract

Fire detection in images has been frequently used recently to detect fire at an early stage. These methods play an important role in reducing the loss of life and property. Fire is not only chemically complex, but also physically very complex. The shape and color of the flame varies according to the type of fuel in the fire. This has made fire detection a very challenging problem. Advanced image processing algorithms are also needed to accurately detect fire. To solve this problem, a three-stage fire framework was created in this study. In the first stage, the flame region was extracted from the images containing the fire region with the basic image processing algorithms. At this stage, reduce brightness, HSL, YCbCr, median and herbaceous filters are applied successively to the image. Since the flame image has a polygonal structure by nature, the number of edges of the flame region has been found. In the second stage, the mobility feature of the flame was utilized. For this purpose, the mobility of the flame was determined by comparing the video frames containing the fire image. The CNN method was used to detect the fire in the images. The CNN model was trained with the transfer learning method using the Inception V3, SequeezeNet, VGG16 and VGG19 trained models. As a result of the tests of the models, 98.8%, 97.0%, 97.3% and 96.8% classification success were obtained, respectively. With the proposed fire detection framework, it is thought that the damage caused by the fire can be reduced by early detection of the fire and timely intervention.

A Convolutional Neural Network as a Potential Tool for Camouflage Assessment

“…In general, YOLO was able to detect the persons both in photosimulations (Experiments 1 and 2) and in naturalistic stimuli (Experiment 3). The present study is not the first study illustrating that convolutional neural networks (YOLO) are capable to detect camouflaged target objects in different environments [44][45][46]. Whereas the vast majority focused primarily on the detection algorithm performance, in the present study we investigated whether YOLO's is capable to asses camouflage efficiency by comparing its performance with human observer data.…”

Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models

“…Average pooling was used in the architectures in this study. In order to get rid of the overfitting problem, generally, the dropout layer is used in CNN architectures (Bicakci et al., 2020 ; Taspinar et al., 2021a ). This layer randomly discards some neurons in each iteration.…”

Classification of Wheat Rootstock and Their Hybrids According to Color Features by Machine Learning Algorithms

“…Confusion matrices were used to determine the performance of the machine learning algorithms [23]. To obtain the confusion matrices values the formulas are shown in Eqs 1-5 [24], [25]were employed with the python SciKitlearn library. Additionally, receiver operating characteristic (ROC) score, is one of the probabilistic forecasting performance measurement method was determined [26].…”